All files of the document are available at: “C:/Users/praha/OneDrive - The Pennsylvania State University/PSU Research Work/Groundwater & Air Pollution/0_DC_GWAP/0_DC_GWAP”
Using cleaned and compiled data for NDVI,GW, & AOD. Data is compiled for all possible states but for analysis, I am considering 17 states as listed in “State_list17”. For GWL, data for state of “Telangana” is missing. Also, data for the year Rajasthan in year 2004 is missing.
For Rajasthan 2004, mean of 2003 and 2005 is imputed as 2004 value for the trend plots and Synthetic Control as they need balanced panel. For regression analysis, Rajasthan:2004 is left “NA”. Use the pre-compiled data for the 14 states
#> [1] "AOD_Filter20_SC_05_13.csv" "Dist_AT_AVG_Period_17States.csv"
#> [3] "DoY_RF_Fire_Data_PB_HR.xlsx" "GW_Filter19_SC_05_13.csv"
#> [5] "GW_Filter19_SC_05_13_RJ_imp.csv" "NDVI_Filter20_SC_05_13.csv"
#> [7] "NDVI_Synth_07_30.csv" "Synth_GW_05_13.csv"
Figure A1(A1). Gridded NDVI data
Figure A1(A2). Gridded AOD data availability for P1
Here the count provides number of records available in each periods of 41 days length. records include 2 satellite data surces so there shall be 41x2=82 records for each grid pixel for complete data availability. (Year 2002 for Perid 1 has only 1 satellite operational(Aqua Satellite was launched on May 4, 2002)).
Figure A1(A3). Gridded AOD data availability for P2
Figure A1(A4). Gridded Average AOD level in P1
Average AOD level is counted using all the available records for each grid pixel.
Figure A1(A5). Average AOD level in P2
| Table A1(B1): NDVI Summary Statistics | |||||||
| Post | Tr_State | Count | Mean | Min | Max | SD | |
|---|---|---|---|---|---|---|---|
| 1 | 0 | 0 | 105 | 0.42 | 0.15 | 0.73 | 0.11 |
| 2 | 0 | 1 | 14 | 0.31 | 0.24 | 0.40 | 0.05 |
| 3 | 1 | 0 | 120 | 0.42 | 0.16 | 0.71 | 0.11 |
| 4 | 1 | 1 | 16 | 0.27 | 0.20 | 0.38 | 0.05 |
| Table A1(B2): Groundwater Level Summary Statistics | |||||||
| Post | Tr_State | Count | Mean | Min | Max | SD | |
|---|---|---|---|---|---|---|---|
| 1 | 0 | 0 | 98 | 7.88 | 4.55 | 16.92 | 2.71 |
| 2 | 0 | 1 | 14 | 10.01 | 9.22 | 11.07 | 0.43 |
| 3 | 1 | 0 | 112 | 7.70 | 4.54 | 16.48 | 2.56 |
| 4 | 1 | 1 | 16 | 10.58 | 8.56 | 11.77 | 0.98 |
| Table A1(B3): AOD Level Summary Statistics | ||||||||
| Post | Tr_State | Period | Count | Mean | Min | Max | SD | |
|---|---|---|---|---|---|---|---|---|
| 1 | 0 | 0 | 0 | 120 | 0.33 | 0.19 | 0.58 | 0.09 |
| 2 | 0 | 0 | 1 | 105 | 0.34 | 0.14 | 0.80 | 0.13 |
| 3 | 0 | 1 | 0 | 16 | 0.42 | 0.34 | 0.54 | 0.06 |
| 4 | 0 | 1 | 1 | 14 | 0.73 | 0.63 | 0.93 | 0.09 |
| 5 | 1 | 0 | 0 | 105 | 0.39 | 0.20 | 0.63 | 0.09 |
| 6 | 1 | 0 | 1 | 120 | 0.47 | 0.18 | 1.02 | 0.16 |
| 7 | 1 | 1 | 0 | 14 | 0.46 | 0.36 | 0.61 | 0.07 |
| 8 | 1 | 1 | 1 | 16 | 0.86 | 0.64 | 1.09 | 0.12 |
First Plotting the period-wise separate plots and then using
difference in Log(AOD) for Period 1 and Period 2 for DiD visualization.
A2(A1). NDVI_M1. Plotting NDVI TWFE Model w/o any control
A2(A2). NDVI_M2. Plotting NDVI TWFE Model w/ May and June RF control
A2(A3). NDVI_M3. Plotting NDVI TWFE Model w/ May and June RF, June
Temp control
A2(A4). NDVI_M4. Plotting log(NDVI)-Linear Control TWFE Model w/ May
and June RF, June Temp control
(Used in the Paper)
A2(B1). GWL_M1. Plotting GWL TWFE Model w/o any control
A2(B2). GWL_M2. Plotting GWL TWFE Model w/ May RF control
A2(B3). GWL_M3. Plotting GWL TWFE Model w/ May RF & May TP
control
A2(B4). GWL_M4. Plotting Log(GWL)-linear control TWFE Model w/ May RF
& May TP control
(Used in the Paper)
A2(C1). AOD_M1. Plotting AOD TWFE Model w/o any control
A2(C2). AOD_M2. Plotting AOD TWFE Model w/ P1+P2 RF
A2(C3). AOD_M3. Plotting AOD TWFE Model w/ P1+P2 RF & Temp
A2(C4). AOD_M4. Plotting Log(AOD)-linear control TWFE Model w/ P1+P2
RF & Temp
(Used in the Paper)
Log(NDVI) DiD Regression Table
| Log_NDVI | ||||||
| OLS | felm | |||||
| No FE | Clt. Strd. Err | State FE | State+Year FE | State+Year FE | State+Year FE | |
| (1) | (2) | (3) | (4) | (5) | (6) | |
| Post | 0.006 | 0.006 | 0.006 | |||
| (0.040) | (0.006) | (0.006) | (0.000) | (0.000) | (0.000) | |
| Tr_State | -0.258*** | -0.258** | ||||
| (0.085) | (0.127) | (0.000) | (0.000) | (0.000) | (0.000) | |
| DiD | -0.145 | -0.145*** | -0.145*** | -0.145*** | -0.136*** | -0.136*** |
| (0.117) | (0.023) | (0.023) | (0.040) | (0.040) | (0.039) | |
| Log_Rainfall_May | 0.008 | 0.008 | ||||
| (0.009) | (0.008) | |||||
| Log_Rainfall_June | 0.022* | 0.023 | ||||
| (0.011) | (0.017) | |||||
| Log_Temp_June | 0.218 | |||||
| (2.938) | ||||||
| Constant | -0.918*** | -0.918*** | ||||
| (0.029) | (0.084) | |||||
| State Fixed-Effect | No | No | Yes | Yes | Yes | Yes |
| Year Fixed-Effect | No | No | No | Yes | Yes | Yes |
| Clustered Std. Error | State | State | State+Year | State+Year | State+Year | |
| Control Factors | Log RF(May&June) | Log RF+TP(May&June) | ||||
| Observations | 255 | 255 | 255 | 255 | 255 | 255 |
| R2 | 0.121 | 0.121 | 0.962 | 0.973 | 0.974 | 0.974 |
| Adjusted R2 | 0.111 | 0.111 | 0.960 | 0.969 | 0.970 | 0.970 |
| Residual Std. Error | 0.300 (df = 251) | 0.300 (df = 251) | 0.064 (df = 236) | 0.056 (df = 223) | 0.055 (df = 221) | 0.055 (df = 220) |
| F Statistic | 11.568*** (df = 3; 251) | |||||
| p<0.1; p<0.05; p<0.01 | ||||||
Log(GW) DiD Regression Table
| Log_GW_Level | ||||||
| OLS | felm | |||||
| No FE | Clt. Strd. Err | State FE | State+Year FE | State+Year FE | State+Year FE | |
| (1) | (2) | (3) | (4) | (5) | (6) | |
| Post | -0.011 | -0.011 | -0.019 | |||
| (0.039) | (0.016) | (0.015) | (0.000) | (0.000) | (0.000) | |
| Tr_State | 0.296*** | 0.296*** | ||||
| (0.079) | (0.077) | (0.000) | (0.000) | (0.000) | (0.000) | |
| DiD | 0.063 | 0.063 | 0.071 | 0.071 | 0.071 | 0.070 |
| (0.109) | (0.050) | (0.050) | (0.051) | (0.050) | (0.052) | |
| Log_Rainfall_May | 0.002 | 0.001 | ||||
| (0.016) | (0.017) | |||||
| Log_Rainfall_June | 0.0001 | 0.0002 | ||||
| (0.0002) | (0.0002) | |||||
| Log_Temp_May | -1.093 | |||||
| (4.128) | ||||||
| Log_Temp_June | 0.008 | |||||
| (0.015) | ||||||
| Constant | 2.007*** | 2.007*** | ||||
| (0.028) | (0.077) | |||||
| State Fixed-Effect | No | No | Yes | Yes | Yes | Yes |
| Year Fixed-Effect | No | No | No | Yes | Yes | Yes |
| Clustered Std. Error | State | State | State+Year | State+Year | State+Year | |
| Control Factors | Log RF (May) | Log RF+TP (May) | ||||
| Observations | 239 | 239 | 239 | 239 | 239 | 239 |
| R2 | 0.137 | 0.137 | 0.927 | 0.939 | 0.939 | 0.939 |
| Adjusted R2 | 0.126 | 0.126 | 0.922 | 0.930 | 0.930 | 0.929 |
| Residual Std. Error | 0.278 (df = 235) | 0.278 (df = 235) | 0.083 (df = 221) | 0.079 (df = 208) | 0.079 (df = 206) | 0.079 (df = 204) |
| F Statistic | 12.406*** (df = 3; 235) | |||||
| p<0.1; p<0.05; p<0.01 | ||||||
Log(AOD) DDD Regression Table
| Dependent variable: | |||
| Log_AOD | |||
| Control Period | Treatment Period | ||
| (1) | (2) | (3) | |
| Tr_State | |||
| (0.000) | (0.000) | (0.000) | |
| Post | -0.067** | ||
| (0.000) | (0.000) | (0.030) | |
| Period | 0.107 | ||
| (0.091) | |||
| DiD | -0.043 | -0.107* | -0.104* |
| (0.077) | (0.058) | (0.056) | |
| DDD | -0.038 | ||
| (0.042) | |||
| Log_Rainfall_P | -0.041 | 0.032* | -0.037** |
| (0.025) | (0.017) | (0.014) | |
| Log_Temp_P | 19.038 | 25.032** | 3.821 |
| (11.851) | (9.540) | (5.803) | |
| Post:Period | 0.141*** | ||
| (0.043) | |||
| Tr_State:Period | 0.425*** | ||
| (0.063) | |||
| State Fixed-Effect | Yes | Yes | |
| Year Fixed-Effect | Yes | Yes | |
| Clustered Std. Error | State+Year | State+Year | |
| Control Factors | Log RF+TP (P1&P2) | Log RF+TP (P1&P2) | |
| Observations | 255 | 255 | 510 |
| R2 | 0.763 | 0.900 | 0.756 |
| Adjusted R2 | 0.728 | 0.885 | 0.736 |
| Residual Std. Error | 0.140 (df = 221) | 0.142 (df = 221) | 0.184 (df = 471) |
| p<0.1; p<0.05; p<0.01 | |||
| Log_AOD | |||||||
| No FE | Clt. Strd. Err | State FE | State+Year FE | State+Year FE | State+Year FE | State+Year FE | |
| (1) | (2) | (3) | (4) | (5) | (6) | (7) | |
| Tr_State | 0.291*** | 0.291*** | |||||
| (0.079) | (0.056) | (0.000) | (0.000) | (0.000) | (0.000) | (0.000) | |
| Post | 0.187*** | 0.187*** | 0.187*** | -0.089* | -0.065* | -0.067** | -0.066** |
| (0.037) | (0.037) | (0.037) | (0.046) | (0.033) | (0.030) | (0.030) | |
| Period | 0.023 | 0.023 | 0.023 | 0.035 | 0.058 | 0.107 | 0.090 |
| (0.037) | (0.055) | (0.055) | (0.057) | (0.053) | (0.091) | (0.089) | |
| DiD | -0.125 | -0.125*** | -0.125*** | -0.148** | -0.117** | -0.104* | -0.098 |
| (0.108) | (0.036) | (0.036) | (0.060) | (0.054) | (0.056) | (0.060) | |
| DDD | -0.018 | -0.018 | -0.018 | 0.006 | -0.031 | -0.038 | -0.037 |
| (0.153) | (0.016) | (0.016) | (0.045) | (0.040) | (0.042) | (0.047) | |
| Log_Rainfall_P | -0.040** | -0.037** | -0.039** | ||||
| (0.014) | (0.014) | (0.013) | |||||
| Log_Temp_P | 3.821 | 3.269 | |||||
| (5.803) | (5.674) | ||||||
| Post:Period | 0.121** | 0.121*** | 0.121*** | 0.132** | 0.142*** | 0.141*** | 0.151*** |
| (0.053) | (0.018) | (0.018) | (0.059) | (0.046) | (0.043) | (0.044) | |
| Tr_State:Period | 0.508*** | 0.508*** | 0.508*** | 0.496*** | 0.426*** | 0.425*** | 0.422*** |
| (0.112) | (0.063) | (0.062) | (0.073) | (0.061) | (0.063) | (0.067) | |
| Constant | -1.149*** | -1.149*** | |||||
| (0.025) | (0.056) | ||||||
| State Fixed-Effect | No | No | Yes | Yes | Yes | Yes | Yes |
| Year Fixed-Effect | No | No | No | Yes | Yes | Yes | Yes |
| Clustered Std. Error | State | State | State+Year | State+Year | State+Year | State+Year | |
| Control Factors | Log RF (P1&P2) | Log RF+TP (P1&P2) | Log RF+TP (P1&P2) | ||||
| Observations | 510 | 510 | 510 | 510 | 510 | 510 | 476 |
| R2 | 0.396 | 0.396 | 0.702 | 0.742 | 0.755 | 0.756 | 0.746 |
| Adjusted R2 | 0.387 | 0.387 | 0.689 | 0.723 | 0.736 | 0.736 | 0.724 |
| Residual Std. Error | 0.281 (df = 502) | 0.281 (df = 502) | 0.200 (df = 487) | 0.189 (df = 473) | 0.184 (df = 472) | 0.184 (df = 471) | 0.185 (df = 438) |
| p<0.1; p<0.05; p<0.01 | |||||||
Here I am excluding U.P. and Bihar states from the control group due to spillover of pollutant transfer. The Event study and regression is re-estimated with 2 less states for control.
#> [1] "Andhra Pradesh" "Bihar" "Chhattisgarh" "Gujarat"
#> [5] "Haryana" "Jharkhand" "Karnataka" "Kerala"
#> [9] "Madhya Pradesh" "Maharashtra" "Orissa" "Punjab"
#> [13] "Rajasthan" "Tamilnadu" "Uttar Pradesh" "West Bengal"
A4(A1). NDVI_M5. Plotting Log(NDVI)-Log Control TWFE Model w/ May and
June RF, June Temp control (12 States)
A4(A2). GWL_M5. Plotting Log(GWL)-Log control TWFE Model w/ May RF
& May TP control (12 States)
A4(A3). AOD_M5. Plotting Log(AOD)-Log control TWFE Model w/ P1+P2 RF
& Temp 12 (12 States)
A4(B1). Log(NDVI) DiD Regression Table (W/ Robustness Check)
| Log_NDVI | |||||||
| OLS | felm | ||||||
| No FE | Clt. Strd. Err | State FE | State+Year FE | State+Year FE | State+Year FE | State+Year FE | |
| (1) | (2) | (3) | (4) | (5) | (6) | (7) | |
| DiD | -0.145 | -0.145*** | -0.145*** | -0.145*** | -0.136*** | -0.136*** | -0.136*** |
| (0.117) | (0.023) | (0.023) | (0.040) | (0.040) | (0.039) | (0.041) | |
| State Fixed-Effect | No | No | Yes | Yes | Yes | Yes | Yes |
| Year Fixed-Effect | No | No | No | Yes | Yes | Yes | Yes |
| Clustered Std. Error | State | State | State+Year | State+Year | State+Year | State+Year | |
| Control Factors | Log RF(May&June) | Log RF+TP(May&June) | Log RF+TP(May&June) | ||||
| Control States | 15 | 15 | 15 | 15 | 15 | 15 | 13 |
| Observations | 255 | 255 | 255 | 255 | 255 | 255 | 225 |
| R2 | 0.121 | 0.121 | 0.962 | 0.973 | 0.974 | 0.974 | 0.974 |
| Adjusted R2 | 0.111 | 0.111 | 0.960 | 0.969 | 0.970 | 0.970 | 0.970 |
| Residual Std. Error | 0.300 (df = 251) | 0.300 (df = 251) | 0.064 (df = 236) | 0.056 (df = 223) | 0.055 (df = 221) | 0.055 (df = 220) | 0.058 (df = 192) |
| F Statistic | 11.568*** (df = 3; 251) | ||||||
| p<0.1; p<0.05; p<0.01 | |||||||
A4(B2). Log(GW) DiD Regression Table (W/ Robustness Check)
| Log_GW_Level | |||||||
| OLS | felm | ||||||
| No FE | Clt. Strd. Err | State FE | State+Year FE | State+Year FE | State+Year FE | State+Year FE | |
| (1) | (2) | (3) | (4) | (5) | (6) | (7) | |
| DiD | 0.063 | 0.063 | 0.071 | 0.071 | 0.071 | 0.070 | 0.083 |
| (0.109) | (0.050) | (0.050) | (0.051) | (0.050) | (0.052) | (0.052) | |
| State Fixed-Effect | No | No | Yes | Yes | Yes | Yes | Yes |
| Year Fixed-Effect | No | No | No | Yes | Yes | Yes | Yes |
| Clustered Std. Error | State | State | State+Year | State+Year | State+Year | State+Year | |
| Control Factors | Log RF (May) | Log RF+TP (May) | Log RF+TP (May) | ||||
| Control States | 14 | 14 | 14 | 14 | 14 | 14 | 12 |
| Observations | 239 | 239 | 239 | 239 | 239 | 239 | 209 |
| R2 | 0.137 | 0.137 | 0.927 | 0.939 | 0.939 | 0.939 | 0.942 |
| Adjusted R2 | 0.126 | 0.126 | 0.922 | 0.930 | 0.930 | 0.929 | 0.932 |
| Residual Std. Error | 0.278 (df = 235) | 0.278 (df = 235) | 0.083 (df = 221) | 0.079 (df = 208) | 0.079 (df = 206) | 0.079 (df = 204) | 0.078 (df = 178) |
| F Statistic | 12.406*** (df = 3; 235) | ||||||
| p<0.1; p<0.05; p<0.01 | |||||||
A4(B3). Log(AOD) DDD Regression Table (W/ Robustness Check)
| Log_AOD | |||||||
| No FE | Clt. Strd. Err | State FE | State+Year FE | State+Year FE | State+Year FE | State+Year FE | |
| (1) | (2) | (3) | (4) | (5) | (6) | (7) | |
| DDD | -0.018 | -0.018 | -0.018 | 0.006 | -0.031 | -0.038 | -0.027 |
| (0.153) | (0.016) | (0.016) | (0.045) | (0.040) | (0.042) | (0.048) | |
| State Fixed-Effect | No | No | Yes | Yes | Yes | Yes | Yes |
| Year Fixed-Effect | No | No | No | Yes | Yes | Yes | Yes |
| Clustered Std. Error | State | State | State+Year | State+Year | State+Year | State+Year | |
| Control Factors | Log RF (P1&P2) | Log RF+TP (P1&P2) | Log RF+TP (P1&P2) | ||||
| Control States | 15 | 15 | 15 | 15 | 15 | 15 | 13 |
| Observations | 510 | 510 | 510 | 510 | 510 | 510 | 450 |
| R2 | 0.396 | 0.396 | 0.702 | 0.742 | 0.755 | 0.756 | 0.748 |
| Adjusted R2 | 0.387 | 0.387 | 0.689 | 0.723 | 0.736 | 0.736 | 0.726 |
| Residual Std. Error | 0.281 (df = 502) | 0.281 (df = 502) | 0.200 (df = 487) | 0.189 (df = 473) | 0.184 (df = 472) | 0.184 (df = 471) | 0.178 (df = 413) |
| p<0.1; p<0.05; p<0.01 | |||||||
A4(C). Exporting the LaTeX tables (Make Changes)
(1)Combined Punjab and Haryana for treatment (2)Andhra Pradesh and Telangana data is pro-rated for synthetic control pre-2014 period as the erstwhile state of Andhra Pradesh was bifurcated into two states in 2014.
P.S: Unfortunately the synthetic control plot commands are not conducive
for making colorful illustrations like ggplot2. Hence, the B/W charts
are used in for synthetic control analysis.
| Control State | Weights | Weights (Backdating 1 Yr) | Weights (Backdating 2 Yr) |
|---|---|---|---|
| Andhra Pradesh | 0.006 | 0.011 | 0.006 |
| Bihar | 0.003 | 0.007 | 0.004 |
| Chhattisgarh | 0.011 | 0.010 | 0.014 |
| Gujarat | 0.008 | 0.022 | 0.008 |
| Jharkhand | 0.006 | 0.010 | 0.006 |
| Karnataka | 0.005 | 0.009 | 0.004 |
| Kerala | 0.004 | 0.006 | 0.003 |
| Madhya Pradesh | 0.017 | 0.021 | 0.016 |
| Maharashtra | 0.003 | 0.011 | 0.004 |
| Orissa | 0.003 | 0.007 | 0.005 |
| Rajasthan | 0.317 | 0.307 | 0.318 |
| Tamilnadu | 0.005 | 0.010 | 0.006 |
| Uttar Pradesh | 0.611 | 0.562 | 0.604 |
| West Bengal | 0.003 | 0.007 | 0.003 |
| Treated | Synthetic | Sample Mean | Treated (BD1) | Synthetic (BD1) | Sample Mean (BD1) | Treated (BD2) | Synthetic (BD2) | Sample Mean (BD2) | |
|---|---|---|---|---|---|---|---|---|---|
| Rainfall(May) | 22.491 | 18.555 | 65.399 | 18.712 | 19.033 | 66.944 | 19.115 | 15.918 | 69.218 |
| Temperature (May) | 305.286 | 306.039 | 304.282 | 305.489 | 306.079 | 304.317 | 305.481 | 306.240 | 304.311 |
| Rainfall(June) | 79.172 | 133.970 | 216.791 | 59.179 | 114.993 | 207.459 | 53.509 | 109.260 | 195.073 |
| Temperature (June) | 305.703 | 305.438 | 302.716 | 306.096 | 305.648 | 302.929 | 306.092 | 305.816 | 302.963 |
| GW_Level | 10.018 | 10.016 | 7.879 | 9.927 | 9.931 | 7.943 | 9.965 | 9.969 | 7.975 |
| Population | 49299.000 | 135469.873 | 67699.527 | 49299.000 | 129714.016 | 67699.527 | 49299.000 | 134627.396 | 67699.527 |
| SoD | 128.171 | 85.682 | 53.357 | 128.171 | 84.190 | 53.357 | 128.171 | 85.491 | 53.357 |
| GSDP | 22908838.400 | 24331914.513 | 19189419.314 | 21963330.500 | 23161662.083 | 18413476.661 | 20971307.667 | 22432273.047 | 17529701.143 |
| AgGDP | 6828382.000 | 6737116.319 | 3514804.529 | 6221277.750 | 5946515.113 | 3271998.750 | 5699963.333 | 5781119.568 | 3019477.643 |
| Rice Cultivation Area(Kharif) | 3760.930 | 3703.427 | 1442.370 | 3714.620 | 3441.098 | 1434.119 | 3725.303 | 3664.033 | 1435.945 |
| Weights | Weights (Backdating 1 Yr) | Weights (Backdating 2 Yr) | |
|---|---|---|---|
| Rainfall(May) | 0.013 | 0.041 | 0.065 |
| Temperature (May) | 0 | 0.012 | 0 |
| Rainfall(June) | 0 | 0 | 0 |
| Temperature (June) | 0.03 | 0.103 | 0.071 |
| GW_Level | 0.806 | 0.79 | 0.766 |
| Population | 0 | 0.001 | 0 |
| SoD | 0 | 0 | 0 |
| GSDP | 0.045 | 0.009 | 0.017 |
| AgGDP | 0.042 | 0.044 | 0.025 |
| Rice Cultivation Area(Kharif) | 0.063 | 0 | 0.056 |
| Table A6(A): AOD Level Summary Statistics (District-Level Data) | ||||||||
| Post | Tr_State | Period | Count | Mean | Min | Max | SD | |
|---|---|---|---|---|---|---|---|---|
| 1 | 0 | 0 | 0 | 3544 | 0.33 | 0.08 | 1.13 | 0.11 |
| 2 | 0 | 0 | 1 | 3101 | 0.39 | 0.08 | 1.16 | 0.18 |
| 3 | 0 | 1 | 0 | 328 | 0.42 | 0.25 | 0.57 | 0.07 |
| 4 | 0 | 1 | 1 | 287 | 0.71 | 0.30 | 1.22 | 0.17 |
| 5 | 1 | 0 | 0 | 3101 | 0.39 | 0.11 | 0.85 | 0.12 |
| 6 | 1 | 0 | 1 | 3544 | 0.52 | 0.07 | 1.43 | 0.22 |
| 7 | 1 | 1 | 0 | 287 | 0.45 | 0.25 | 0.68 | 0.08 |
| 8 | 1 | 1 | 1 | 328 | 0.84 | 0.28 | 1.50 | 0.23 |
Call: felm(formula = Log_AOD ~ relevel(factor(Time_To_Treatment *
Tr_State * Period), ref = “-1”) + Period + Tr_State * Post + Tr_State *
Period + Period * Post + Log_Rainfall + Log_Temp | State + Year | 0 |
State + Year, data = dt)
Residuals: Min 1Q Median 3Q Max -1.40137 -0.16220 0.00899 0.16992 1.48036
Coefficients: Estimate relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-7 1.234e-01 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-6 -1.521e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-5 1.041e-01 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-4 3.627e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-3 2.100e-01 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-2 -5.168e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)0 9.661e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)1 5.881e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)2 -2.581e-01 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)3 8.337e-03 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)4 -5.708e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)5 -8.825e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)6 -2.833e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)7 -4.702e-04 Period 3.053e-01 Tr_State NaN Post -1.277e-01 Log_Rainfall -9.470e-03 Log_Temp 1.167e+00 Tr_State:Post -4.235e-02 Period:Tr_State 4.087e-01 Period:Post 1.548e-01 Cluster s.e. relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-7 4.544e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-6 5.355e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-5 4.824e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-4 7.698e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-3 2.139e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-2 2.901e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)0 6.988e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)1 4.401e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)2 3.622e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)3 6.677e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)4 4.106e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)5 2.684e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)6 2.220e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)7 7.370e-02 Period 6.552e-02 Tr_State 3.878e-18 Post 3.013e-02 Log_Rainfall 1.152e-02 Log_Temp 3.593e-01 Tr_State:Post 4.396e-02 Period:Tr_State 6.789e-02 Period:Post 3.906e-02 t value relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-7 2.716 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-6 -0.284 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-5 2.157 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-4 0.471 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-3 9.818 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-2 -1.782 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)0 1.383 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)1 1.336 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)2 -7.124 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)3 0.125 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)4 -1.390 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)5 -3.288 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)6 -1.277 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)7 -0.006 Period 4.660 Tr_State NaN Post -4.237 Log_Rainfall -0.822 Log_Temp 3.248 Tr_State:Post -0.963 Period:Tr_State 6.020 Period:Post 3.963 Pr(>|t|) relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-7 0.016721 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-6 0.780535 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-5 0.048844 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-4 0.644822 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-3 1.17e-07 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-2 0.096524 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)0 0.188473 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)1 0.202758 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)2 5.14e-06 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)3 0.902405 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)4 0.186177 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)5 0.005386 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)6 0.222540 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)7 0.995000 Period 0.000368 Tr_State NaN Post 0.000829 Log_Rainfall 0.424707 Log_Temp 0.005837 Tr_State:Post 0.351700 Period:Tr_State 3.15e-05 Period:Post 0.001415
relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-7
*
relevel(factor(Time_To_Treatment * Tr_State * Period), ref =
“-1”)-6
relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-5
*
relevel(factor(Time_To_Treatment * Tr_State * Period), ref =
“-1”)-4
relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-3
relevel(factor(Time_To_Treatment Tr_State * Period),
ref = “-1”)-2 .
relevel(factor(Time_To_Treatment * Tr_State * Period), ref =
“-1”)0
relevel(factor(Time_To_Treatment * Tr_State * Period), ref =
“-1”)1
relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)2
relevel(factor(Time_To_Treatment Tr_State * Period),
ref = “-1”)3
relevel(factor(Time_To_Treatment * Tr_State * Period), ref =
“-1”)4
relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)5 **
relevel(factor(Time_To_Treatment * Tr_State * Period), ref =
“-1”)6
relevel(factor(Time_To_Treatment * Tr_State * Period), ref =
“-1”)7
Period Tr_State
Post Log_Rainfall
Log_Temp ** Tr_State:Post
Period:Tr_State * Period:Post — Signif. codes: 0
‘’ 0.001 ’’ 0.01 ’’ 0.05 ‘.’ 0.1 ’ ’ 1
Residual standard error: 0.2728 on 14359 degrees of freedom Multiple R-squared(full model): 0.6041 Adjusted R-squared: 0.6027 Multiple R-squared(proj model): 0.2261 Adjusted R-squared: 0.2234 F-statistic(full model, iid):438.3 on 50 and 14359 DF, p-value: < 2.2e-16 F-statistic(proj model): 56.21 on 22 and 14 DF, p-value: 3.882e-10
| Dependent variable: | ||
| Log_AOD | ||
| Control Period | Treatment Period | |
| (1) | (2) | |
| Tr_State | ||
| (0.000) | (0.000) | |
| Post | ||
| (0.000) | (0.000) | |
| Post_Tr_State | -0.057 | -0.120** |
| (0.052) | (0.051) | |
| Log_Rainfall | 0.006 | 0.015 |
| (0.007) | (0.009) | |
| Log_Temp | 1.046** | 2.157*** |
| (0.440) | (0.512) | |
| State Fixed-Effect | Yes | Yes |
| Year Fixed-Effect | Yes | Yes |
| Clustered Std. Error | State+Year | State+Year |
| Control Factors | Log RF+TP (P1&P2) | Log RF+TP (P1&P2) |
| Observations | 7,239 | 7,171 |
| R2 | 0.537 | 0.740 |
| Adjusted R2 | 0.535 | 0.739 |
| Residual Std. Error | 0.234 (df = 7206) | 0.246 (df = 7138) |
| p<0.1; p<0.05; p<0.01 | ||
| Log_AOD | ||||
| State-Level | State-Level | Dist-Level | Dist-Level | |
| (1) | (2) | (3) | (4) | |
| DDD | -0.038 | -0.027 | -0.092** | -0.084* |
| (0.042) | (0.048) | (0.034) | (0.042) | |
| Unit of Analysis | State | State | Dist | Dist |
| State Fixed-Effect | Yes | Yes | Yes | Yes |
| Year Fixed-Effect | Yes | Yes | Yes | Yes |
| Clustered Std. Error | State+Year | State+Year | State+Year | State+Year |
| Control Factors | Log RF+TP (P1&P2) | Log RF+TP (P1&P2) | Log RF+TP (P1&P2) | Log RF+TP (P1&P2) |
| Control States | 15 | 13 | 15 | 13 |
| Observations | 510 | 450 | 14,410 | 11,168 |
| R2 | 0.756 | 0.748 | 0.602 | 0.550 |
| Adjusted R2 | 0.736 | 0.726 | 0.601 | 0.549 |
| Residual Std. Error | 0.184 (df = 471) | 0.178 (df = 413) | 0.273 (df = 14372) | 0.271 (df = 11132) |
| p<0.1; p<0.05; p<0.01 | ||||
Call: felm(formula = Log_AOD ~ relevel(factor(Time_To_Treatment *
Tr_State * Period), ref = “-1”) + Period + Tr_State * Post + Tr_State *
Period + Period * Post + Log_Rainfall + Log_Temp | State + Year | 0 |
State + Year, data = dt)
Residuals: Min 1Q Median 3Q Max -1.39306 -0.16035 0.00485 0.16592 1.50446
Coefficients: Estimate relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-6 -1.844e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-5 9.388e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-4 2.622e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-3 2.104e-01 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-2 -4.063e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)0 6.966e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)1 2.941e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)2 -2.600e-01 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)3 -2.144e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)4 -9.108e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)5 -1.165e-01 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)6 -5.620e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)7 1.161e-02 Period 3.279e-01 Tr_State NaN Post -1.293e-01 Log_Rainfall -1.953e-02 Log_Temp 4.415e-02 Tr_State:Post -2.635e-02 Period:Tr_State 3.405e-01 Period:Post 1.714e-01 Cluster s.e. relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-6 5.161e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-5 3.555e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-4 7.545e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-3 2.370e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-2 2.038e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)0 6.256e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)1 3.901e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)2 3.427e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)3 5.760e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)4 3.452e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)5 2.983e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)6 2.153e-02 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)7 5.344e-02 Period 7.417e-02 Tr_State 1.340e-17 Post 2.577e-02 Log_Rainfall 1.367e-02 Log_Temp 1.564e-02 Tr_State:Post 4.506e-02 Period:Tr_State 6.822e-02 Period:Post 3.724e-02 t value relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-6 -0.357 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-5 2.641 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-4 0.348 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-3 8.877 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-2 -1.994 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)0 1.113 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)1 0.754 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)2 -7.587 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)3 -0.372 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)4 -2.638 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)5 -3.905 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)6 -2.610 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)7 0.217 Period 4.421 Tr_State NaN Post -5.017 Log_Rainfall -1.428 Log_Temp 2.824 Tr_State:Post -0.585 Period:Tr_State 4.991 Period:Post 4.603 Pr(>|t|) relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-6 0.726587 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-5 0.020363 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-4 0.733720 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-3 7.03e-07 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-2 0.067531 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)0 0.285672 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)1 0.464327 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)2 3.97e-06 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)3 0.715751 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)4 0.020459 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)5 0.001809 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)6 0.021588 relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)7 0.831439 Period 0.000691 Tr_State NaN Post 0.000236 Log_Rainfall 0.176825 Log_Temp 0.014359 Tr_State:Post 0.568670 Period:Tr_State 0.000247 Period:Post 0.000495
relevel(factor(Time_To_Treatment * Tr_State * Period), ref =
“-1”)-6
relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-5
*
relevel(factor(Time_To_Treatment * Tr_State * Period), ref =
“-1”)-4
relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)-3
relevel(factor(Time_To_Treatment Tr_State * Period),
ref = “-1”)-2 .
relevel(factor(Time_To_Treatment * Tr_State * Period), ref =
“-1”)0
relevel(factor(Time_To_Treatment * Tr_State * Period), ref =
“-1”)1
relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)2
relevel(factor(Time_To_Treatment Tr_State * Period),
ref = “-1”)3
relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)4
*
relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)5 **
relevel(factor(Time_To_Treatment * Tr_State * Period), ref = “-1”)6
*
relevel(factor(Time_To_Treatment * Tr_State * Period), ref =
“-1”)7
Period Tr_State
Post Log_Rainfall
Log_Temp *
Tr_State:Post
Period:Tr_State Period:Post — Signif. codes:
0 ‘’ 0.001 ’’ 0.01 ’’ 0.05 ‘.’ 0.1 ’ ’ 1
Residual standard error: 0.269 on 13503 degrees of freedom Multiple R-squared(full model): 0.6096 Adjusted R-squared: 0.6082 Multiple R-squared(proj model): 0.2522 Adjusted R-squared: 0.2496 F-statistic(full model, iid):439.3 on 48 and 13503 DF, p-value: < 2.2e-16 F-statistic(proj model): 221.9 on 21 and 13 DF, p-value: 2.355e-13
| Log_AOD | ||||
| State-Level | State-Level | Dist-Level | Dist-Level | |
| (1) | (2) | (3) | (4) | |
| DDD | -0.037 | -0.028 | -0.099** | -0.093** |
| (0.047) | (0.056) | (0.035) | (0.041) | |
| Unit of Analysis | State | State | Dist | Dist |
| State Fixed-Effect | Yes | Yes | Yes | Yes |
| Year Fixed-Effect | Yes | Yes | Yes | Yes |
| Clustered Std. Error | State+Year | State+Year | State+Year | State+Year |
| Control Factors | Log RF+TP (P1&P2) | Log RF+TP (P1&P2) | Log RF+TP (P1&P2) | Log RF+TP (P1&P2) |
| Control States | 15 | 13 | 15 | 13 |
| Observations | 476 | 420 | 13,552 | 10,500 |
| R2 | 0.746 | 0.738 | 0.608 | 0.548 |
| Adjusted R2 | 0.724 | 0.714 | 0.607 | 0.546 |
| Residual Std. Error | 0.185 (df = 438) | 0.179 (df = 384) | 0.270 (df = 13515) | 0.269 (df = 10465) |
| p<0.1; p<0.05; p<0.01 | ||||
[1] “State” “St_Code” “Year”
[4] “NDVI” “Tr_State” “Post”
[7] “DiD” “Rainfall_June” “RainyDays_June”
[10] “Rainfall_May” “RainyDays_May” “Rainfall_P1”
[13] “RainyDays_P1” “Rainfall_P2” “RainyDays_P2”
[16] “Temp_June” “Temp_May” “Temp_P1”
[19] “Temp_P2” “Time_To_Treatment” “Log_NDVI”
[22] “Log_Rainfall_June” “Log_Rainfall_May” “Log_Temp_June”
[25] “Log_Temp_May” “GSDP” “AgGDP”
[28] “Population” “SoD” “RiceT”
[31] “RiceK”
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 0.0001572315
solution.v: 0.05420307 0.1466799 2.7397e-06 0.08877862 0.1472921 0.06709368 0.1221464 0.08372835 4.34372e-05 0.2900317
solution.w: 0.0009475729 0.0001339082 0.04773945 0.0005710098 7.40704e-05 0.0002925387 4.2997e-06 0.0007361399 0.0001684055 0.0001334264 0.3693999 0.1745274 0.0008981431 0.4043738
[1] “tab.pred” “tab.v” “tab.w” “tab.loss” Treated Synthetic Sample
Mean Rainfall_May 22.491 29.592 56.517 Temp_May 305.286 305.731 304.562
Rainfall_June 79.172 115.619 198.549 Temp_June 305.703 305.009 302.823
special.NDVI.2002.2008 0.315 0.315 0.411 special.Population.2006
49299.000 110158.343 63968.964 special.SoD.2004 128.171 90.475 54.429
special.GSDP.2004.2008 22908838.400 22895687.993 18314617.814
special.AgGDP.2004.2008 6828382.000 5500046.323 3318134.971
special.RiceK.2004.2008 3760.930 2921.604 1484.433 v.weights
Rainfall_May 0.054
Temp_May 0.147
Rainfall_June 0
Temp_June 0.089
special.NDVI.2002.2008 0.147
special.Population.2006 0.067
special.SoD.2004 0.122
special.GSDP.2004.2008 0.084
special.AgGDP.2004.2008 0
special.RiceK.2004.2008 0.29
Loss W Loss V [1,] 0.3951706 0.0001572315
w.weight 1 9.475729e-04 2 1.339082e-04 3 4.773945e-02 4 5.710098e-04 5
7.407037e-05 6 2.925387e-04 7 4.299665e-06 8 7.361399e-04 9 1.684055e-04
10 1.334264e-04 11 3.693999e-01 12 1.745274e-01 13 8.981431e-04 14
4.043738e-01 [1] 0.04773945 0.36939991 0.17452741 0.40437377
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 0.000390147
solution.v: 0.01424146 1.3178e-06 0.0406692 0.04075915 0.7698587 0.02155787 7.5e-08 0.003651695 0.1089594 0.0003011593
solution.w: 0.02400693 0.04045245 0.07592969 0.03421162 0.05955377 0.02673113 0.06009503 0.03623124 0.04782634 0.06346042 0.2973092 0.1017849 0.132407
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 0.0001618406
solution.v: 0.01178876 0 0.009809927 0 0.9079972 0.007979565 0.01841646 0.01692064 0.02399703 0.00309043
solution.w: 0.01229246 0.0004090846 0.03072638 0.5803956 0.03092839 0.05587657 0.03815362 0.01259408 1.52531e-05 0.06694794 0.009625234 0.009025644 0.1530098
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 0.000157143
solution.v: 0.04767206 0.002689464 0.03902223 3.22444e-05 0.7763535 0.02961256 0.02967596 0.03168709 0.0377995 0.005455364
solution.w: 0.009866235 0.003891589 0.002651938 0.7081778 0.003677174 0.02473333 0.1292526 0.003499013 0.06803382 0.0006070617 0.003441471 0.03798734 0.00418047
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 4.773238e-06
solution.v: 0.2241937 0.001037908 0.0002311095 2.66916e-05 0.3784413 0.1803174 5.2926e-06 1.0787e-06 0.1464005 0.06934498
solution.w: 0.0394239 0.01577546 0.02529356 0.02055563 0.02486745 0.000365092 0.04392392 0.03362842 0.02079646 0.6966788 0.01596579 0.03245633 0.03026911
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 9.740222e-05
solution.v: 5.162e-07 0.00916579 0.05583244 0.01994815 0.8149031 2.968e-07 1.872e-07 0.09958072 0.0001469166 0.0004218885
solution.w: 0.03301892 0.1039138 0.4539724 0.01225714 0.03023987 0.1235881 0.03424756 0.008330819 0.1070278 0.01184459 0.02333575 0.04263157 0.01559145
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 0.0001903824
solution.v: 1.8229e-06 0.00300845 6.38e-08 0.004840446 0.8045127 0.01537627 0.03973682 0.03551923 0.02903578 0.06796838
solution.w: 0.03076806 0.0222533 0.02312388 0.4124712 0.01909078 0.1868047 0.02084109 5.60705e-05 0.01768754 0.0379909 0.1814683 0.01695653 0.0304874
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 0.03152589
solution.v: 0.01739718 0.0007824561 0.01519618 0.0007706755 0.9220628 0.01309564 0.008844571 0.001242076 0.01921086 0.001397514
solution.w: 7.91066e-05 0.0001233193 0.0001013564 1.36947e-05 2.7049e-06 8.04897e-05 5.1231e-05 6.20843e-05 0.9990416 5.041e-07 0.0002774567 0.0001081957 5.81933e-05
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 8.449551e-05
solution.v: 0.1420808 0.03128715 0.02895621 0.009091418 0.6612678 0.001435262 0.02187938 0.07764148 0.0007896677 0.0255708
solution.w: 0.03806093 0.02747056 0.3354178 0.06525281 0.04069215 0.01879509 0.002604674 0.0376877 0.04945733 0.2249116 0.01694996 0.1039098 0.03878912
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 5.707544e-05
solution.v: 0.123968 0.001106227 0.01519019 0.002038121 0.8367914 0.002641329 0.005204254 0.0001842452 0.01237232 0.0005038329
solution.w: 0.02476911 0.0457056 0.09230854 0.1878266 0.05738182 0.03754688 0.01189864 0.09771222 0.06364703 3.79922e-05 0.01519005 0.03064332 0.3353317
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 0.0002553796
solution.v: 7.9096e-06 0.002290694 0.02704248 0.006565434 0.8065916 0.1035186 0.0085905 1.62272e-05 0.04376386 0.001612773
solution.w: 0.05445954 0.03982485 0.2447029 0.01022447 0.2027556 0.02561016 0.2300446 0.03233548 0.02431132 0.002405432 0.04990447 0.07045275 0.01296765
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 0.005553722
solution.v: 0.001226548 2.98123e-05 0.01744958 1.52e-08 0.9138121 1.70819e-05 0.05726646 2.82814e-05 0.009380906 0.0007892008
solution.w: 5.3616e-06 4.555e-06 3.278e-06 0.9999391 3.0709e-06 7.9267e-06 6.53e-08 7.1418e-06 6.586e-06 2.5415e-06 5.9451e-06 5.318e-06 9.0884e-06
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 0.000477725
solution.v: 0.4171317 0.263623 0.02461644 0.0002058697 0.2485497 0.02658308 0.003794997 0.0004596895 0.0146031 0.000432454
solution.w: 0.07649267 0.06962155 0.04375978 0.05577287 0.06610306 0.1588538 0.2329503 0.04037165 0.05041233 0.06050089 0.03815627 0.04880918 0.05816893
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 0.0002357812
solution.v: 0.002702115 0.03383094 1.25e-08 0.0004617649 0.9239821 0.02457356 4.561e-07 0.01240352 0.002045412 1.757e-07
solution.w: 0.04101174 0.03540497 0.5468453 0.02927511 0.04253958 0.02961962 0.02071286 0.05845103 0.03798982 0.06100433 0.03113061 0.03433458 0.03167972
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 4.060474e-05
solution.v: 0.031969 0.03960776 0.253923 0.00146535 0.1293159 0.03609445 0.07234974 0.2454709 0.1192615 0.07054243
solution.w: 0.1548312 0.01385767 0.01325612 0.06521354 0.0005138363 0.03248193 0.002116777 0.1021564 0.4545884 0.005456847 0.0663869 0.07832924 0.01080214
Backdating for NDVI [1] “State” “St_Code” “Year”
[4] “NDVI” “Tr_State” “Post”
[7] “DiD” “Rainfall_June” “RainyDays_June”
[10] “Rainfall_May” “RainyDays_May” “Rainfall_P1”
[13] “RainyDays_P1” “Rainfall_P2” “RainyDays_P2”
[16] “Temp_June” “Temp_May” “Temp_P1”
[19] “Temp_P2” “Time_To_Treatment” “Log_NDVI”
[22] “Log_Rainfall_June” “Log_Rainfall_May” “Log_Temp_June”
[25] “Log_Temp_May” “GSDP” “AgGDP”
[28] “Population” “SoD” “RiceT”
[31] “RiceK”
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 0.0001834653
solution.v: 0.01474062 0.01221754 0.0007253887 0.005711438 0.9342627 0.003849763 0.008196921 0.0005096298 0.0001520995 0.01963388
solution.w: 0.001306744 0.0003533698 0.02699816 0.0009776205 0.0006563009 0.0002835766 8.6113e-06 0.001460926 0.0004509492 0.0006571908 0.359741 0.1704884 0.002327699 0.4342894
[1] “tab.pred” “tab.v” “tab.w” “tab.loss” Treated Synthetic Sample
Mean Rainfall_May 18.712 28.177 58.400 Temp_May 305.489 305.840 304.593
Rainfall_June 59.179 98.007 190.777 Temp_June 306.096 305.360 303.031
special.NDVI.2002.2007 0.314 0.314 0.413 special.Population.2006
49299.000 114499.714 63968.964 special.SoD.2004 128.171 90.807 54.429
special.GSDP.2004.2007 21963330.500 22588919.021 17542022.071
special.AgGDP.2004.2007 6221277.750 5236069.497 3076591.411
special.RiceK.2004.2007 3714.620 2987.381 1473.604 v.weights
Rainfall_May 0.015
Temp_May 0.012
Rainfall_June 0.001
Temp_June 0.006
special.NDVI.2002.2007 0.934
special.Population.2006 0.004
special.SoD.2004 0.008
special.GSDP.2004.2007 0.001
special.AgGDP.2004.2007 0
special.RiceK.2004.2007 0.02
Loss W Loss V [1,] 0.0251982 0.0001834653
w.weight 1 1.306744e-03 2 3.533698e-04 3 2.699816e-02 4 9.776205e-04 5
6.563009e-04 6 2.835766e-04 7 8.611303e-06 8 1.460926e-03 9 4.509492e-04
10 6.571908e-04 11 3.597410e-01 12 1.704884e-01 13 2.327699e-03 14
4.342894e-01 [1] 0.02699816 0.35974097 0.17048844 0.43428944
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 0.0004297768
solution.v: 0.01539953 3.00135e-05 0.06091758 0.03476192 0.8409411 0.0003727625 1.4589e-06 0.006448066 0.04048974 0.0006378567
solution.w: 0.0388082 0.04290803 0.05707911 0.04115846 0.0552999 0.0240503 0.0596887 0.03392734 0.0445168 0.06265216 0.323367 0.06076371 0.1557802
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 0.0001902658
solution.v: 0.007341279 0.0006134711 0.007741028 0.007456296 0.7032537 0.03702132 0.07225765 0.08477568 0.05411017 0.02542943
solution.w: 0.01513672 0.004434681 0.01717301 0.6066838 0.02356524 0.02788459 0.05036396 0.009915665 5.11358e-05 0.05360277 0.01401906 0.01924931 0.1579189
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 0.0001672026
solution.v: 0.01653482 2.018e-07 0.01875611 0.0003036871 0.9111141 0.01565113 0.006228153 0.003875076 0.02750926 2.74454e-05
solution.w: 0.01439435 0.01123235 0.01098625 0.8141388 0.0116746 2.46008e-05 0.01339223 0.01115662 0.06236638 0.009857567 0.0125107 0.01902463 0.009240918
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 4.156468e-06
solution.v: 0.04313074 0.0004506939 0.0001049299 0.000275774 0.9200634 0.02686096 4.04389e-05 5.07508e-05 0.005338803 0.003683523
solution.w: 0.03386124 0.01921729 0.02924747 0.02290753 0.02716177 0.0002956066 0.04375855 0.03064474 0.01919467 0.7016937 0.01759272 0.03108268 0.02334203
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 7.187783e-05
solution.v: 0.05163404 0.01330034 0.1156328 0.0136701 0.4926305 0.0003725365 0.0001535593 0.1841378 0.1219092 0.006559062
solution.w: 0.02131204 0.07202588 0.5126119 0.01039037 0.02387305 0.09315691 0.02617816 0.0007220725 0.1333293 0.01711536 0.01931237 0.069424 0.0005480166
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 0.0001945098
solution.v: 8.6855e-06 0.03557503 4.24509e-05 7.02265e-05 0.8663435 0.0002075417 0.0618592 0.02012141 0.0157718 1.192e-07
solution.w: 0.0360906 0.0369568 0.02362653 0.3598381 0.03171238 0.1012647 0.02569943 0.01928791 0.02582434 5.20616e-05 0.2914445 0.0219341 0.02626672
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 0.03201685
solution.v: 0.02611704 0.00101616 0.01610771 0.0006062854 0.9083837 0.01579127 1.0548e-06 0.007111219 0.02110603 0.003759487
solution.w: 6.85955e-05 0.0001040305 7.19489e-05 1.13972e-05 2.243e-06 7.05831e-05 4.12317e-05 5.57236e-05 0.9992595 4.241e-07 0.0001832766 8.40577e-05 4.68945e-05
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 8.717209e-05
solution.v: 0.1044679 0.03834056 5.71781e-05 0.002362734 0.7387023 0.008676266 0.03001521 0.05585324 0.01985206 0.001672564
solution.w: 0.04536292 0.03764575 0.2893962 0.06226185 0.04302019 0.01966552 0.003637495 0.04092295 0.05527895 0.2169319 0.01615411 0.09189015 0.07783137
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 6.191272e-05
solution.v: 0.0975725 0.01435528 0.001754693 9.7274e-05 0.8812646 0.00178515 0.001028101 4.6228e-06 0.002033567 0.0001042607
solution.w: 0.04890979 0.04757251 0.06250943 0.1468502 0.04756994 0.04269754 0.01506655 0.1243117 0.04938156 0.02300381 0.03436916 0.05627926 0.3014783
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 0.0002704445
solution.v: 1.56826e-05 1.04542e-05 0.002618007 0.004978862 0.6828858 0.2301376 0.008075333 0.0002770502 0.02214933 0.04885185
solution.w: 0.04655873 0.03601251 0.0883803 0.01499596 0.3952575 0.02947458 0.2389687 0.03176546 0.02405409 0.006533118 0.03551285 0.04502319 0.007462872
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 0.005753193
solution.v: 2.3131e-05 6.9711e-06 3.37624e-05 0.0005944112 0.5065161 0.003247884 0.2654854 0.006194506 0.06586211 0.1520357
solution.w: 6.746e-07 7.592e-07 2.249e-07 0.9999782 3.526e-07 4.1014e-06 2.85e-08 1.0821e-06 9.611e-07 2.362e-07 9.118e-06 1.7245e-06 2.4999e-06
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 0.0004174575
solution.v: 0.3320291 0.2218404 0.0465115 0.08822582 0.2353049 0.003702537 0.0002245648 0.0005923757 0.06895406 0.002614741
solution.w: 0.08499069 0.06651593 0.04737238 0.0570897 0.07026909 0.1536539 0.2174612 0.0437761 0.04602646 0.06367093 0.04062202 0.05176306 0.05675901
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 0.0001687669
solution.v: 4.5169e-06 4e-09 2.807e-07 1.155e-07 0.3887981 0.1581301 0.004566336 0.1895181 0.2498084 0.009173931
solution.w: 0.0430084 0.003839029 0.2186553 0.05830709 0.2614588 0.01310592 0.2028703 0.008094201 0.005122725 0.01229422 0.1636669 0.007318348 0.00225875
X1, X0, Z1, Z0 all come directly from dataprep object.
searching for synthetic control unit
MSPE (LOSS V): 1.961699e-05
solution.v: 0.004706325 0.00067057 0.0004105874 0.004706322 0.7520816 0.008783959 0.01856575 0.07940867 0.1225698 0.008096391
solution.w: 0.2314492 0.002820999 0.0007824972 0.05523455 0.0005929791 0.006473165 0.0001280334 0.01944595 0.6274088 0.0008995846 0.05107187 0.002142082 0.001550174
Exporting Final Stargazer Tables
% Table created by stargazer v.5.2.3 by Marek Hlavac, Social Policy Institute. E-mail: marek.hlavac at gmail.com % Date and time: Wed, Mar 05, 2025 - 10:46:57 AM % Table created by stargazer v.5.2.3 by Marek Hlavac, Social Policy Institute. E-mail: marek.hlavac at gmail.com % Date and time: Wed, Mar 05, 2025 - 10:47:00 AMP.S.: Prepared for PhD Dissertation: Praharsh M. Patel {Ph.D.: Energy, Environmental, and Food Economics}